Dev Loop Readme Writer
Use when the user asks to write a README for this repository, improve project documentation, add quick start, installation, usage or contributing sections, or badges. Produces a structured README.md. Not for API reference docs (use backend-openapi-documentation) or changelogs (use dev-loop-changelog-generator).
Install
npx skills add j4flmao/agent-skills --skill dev-loop-readme-writergit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/dev-loop/readme-writer ~/.claude/skills/dev-loop-readme-writerPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# README Writer
## Purpose
Write clear, structured, and effective README files that help users and contributors understand, install, use, and contribute to a project. A great README is the single most important documentation page for any project.
## Agent Protocol
### Trigger
Exact user phrases: "write README", "create README", "README file", "README.md", "project documentation", "project README", "README template", "improve README".
### Input Context
- Project name and description
- Project type (CLI tool, library, web app, API server, desktop app, game)
- Language and framework (Node.js, Python, Rust, Go, .NET, etc.)
- Target audience (end users, developers, both)
- Installation method (npm, pip, cargo, Docker, Homebrew, manual)
- Build and test commands
- Configuration options and environment variables
- Contributing guidelines (if available)
- License type
- Badges (CI status, coverage, version, license)
### Output Artifact
README.md file following the project's conventions and audience needs.
### Response Format
```
# {Project} — {one-line value statement}
{badges}
## Installation
## Quick Start
## Usage / Configuration
## Development
## Contributing
## License
```
### Completion Criteria
- [ ] Project name and one-line description at top
- [ ] Badges (CI status, version, license, coverage)
- [ ] Table of Contents (if README is long)
- [ ] Installation instructions (platform-specific if needed)
- [ ] Quick start / usage exampleDetails
- Skill name
dev-loop-readme-writer- Repository
- j4flmao/agent-skills
- Path
skills/dev-loop/readme-writer/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Dev Loop Readme Writer skill do?
Use when the user asks to write a README for this repository, improve project documentation, add quick start, installation, usage or contributing sections, or badges. Produces a structured README.md. Not for API reference docs (use backend-openapi-documentation) or changelogs (use dev-loop-changelog-generator).
How do I install the Dev Loop Readme Writer skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill dev-loop-readme-writer. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Dev Loop Readme Writer popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Frontend Storybook
45j4flmao/agent-skills
Use when the user asks to document button variants or other components in Storybook, CSF 3 stories, args and controls, play functions, interaction or a11y tests in Storybook, Chromatic visual tests or Storybook config. Produces stories, docs and test setup for Storybook 9+. Not for general unit and E2E testing (use frontend-testing).
Data Formats
45j4flmao/agent-skills
Use when the user asks about Parquet vs ORC vs Avro, Apache Arrow, Arrow Flight, row group size, encoding and compression (ZSTD, Snappy) or columnar vs row-oriented formats. Produces a format choice and writer settings for the access pattern. Not for table formats like Iceberg or Delta (use data-data-lake).
Handoff Doc
23nathanonn/agent-skills
Write or update a session handoff doc that lets a future session (Claude or human) resume work without re-reading the whole transcript. Use this skill whenever the user asks to "write a handoff", "create a handoff doc", "update the handoff", "write a doc so the next session can continue", "session handoff note", "hand this off", or points at a path and says to capture where things stand. The user only needs to give the destination file path — the content is distilled from the current session. Do NOT use for general project documentation, READMEs, API docs, code comments, or changelogs.
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.